Visual anomaly detection (VAD) aims to identify image regions that deviate from established normal patterns. Existing methods often rely on domain-specific training and follow a ''one-class-one-model'' paradigm, limiting scalability. We propose Omni-LLaMA-AD, the first unified multimodal large language model for open-set anomaly detection, capable of handling diverse domains with minimal supervision. Built on a pretrained LLaMA backbone, the model uses a VQGAN-based tokenizer and supports joint vision-language generation. Trained via vision-language alignment and instruction tuning, it achieves effective anomaly detection with only a few normal samples and no domain-specific fine-tuning. Our demo showcases the model's ability to generate high-quality anomaly masks across industrial, medical, and logical datasets, highlighting its strong cross-domain generalization and interactive dialogue-based user experience.

The traditional controllable face generation refers to the controllability of coarse-grained ranges such as facial features, expression postures, or viewing angles, but specific application scenarios require finer-grained control. This paper proposes a fine-grained and controllable face generation technology, CFTF. CFTF allows users to participate deeply in the face generation process through multiple rounds of language feedback. It not only enables control over coarse-grained features such as gender and viewing angle, but also provides flexible control over details such as hair color, accessories, and iris color. We apply CFTF to the suspect portrait scene, and perform multiple rounds of human-computer interaction based on the eyewitness's painting sketch of the suspect and descriptions of their facial features, realizing the "Human-in-the-loop" collaborative portrait drawing.